# Image Synthesis on NANO-TEM synthetic samples n=6656

Source: [Image Synthesis on NANO-TEM synthetic samples n=6656](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T08:56:01.020Z

Evaluation of image synthesis models on the NANO-TEM synthetic samples dataset (n=6656), typically measured using fidelity metrics (PSNR, SSIM, LPIPS) and distributional metrics (FID, KID).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Synthesis |
| Dataset (including any stated split) | NANO-TEM synthetic samples n=6656 |
| Metric | MS-SSIM |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 20 of 20 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [MS-SSIM](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=MS-SSIM>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [MSE](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=MSE>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/image-synthesis-on-nano-tem-synthetic-samples-n-6656.md?metric=KID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MS-SSIM | Result date | Report paper |
| --- | --- | --- | --- |
| MS-SSIM VAE | 0.587 | Not recorded | 6a3b64e7206542251d7c9a5e |
| VAE | 0.587 | Not recorded | 6a3b64e7206542251d7c9a5e |
| MS-SSIM VAE | 0.579 | Not recorded | 6a3b64e7206542251d7c9a5e |
| VAE | 0.579 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.508 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.508 | Not recorded | 6a3b64e7206542251d7c9a5e |
| patch-based progressive training methodology for DDPMs | 0.481 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Ours | 0.481 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.472 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.472 | Not recorded | 6a3b64e7206542251d7c9a5e |
| patch-based progressive training methodology for DDPMs | 0.414 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Ours | 0.414 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Baseline DDPM | 0.412 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Base | 0.412 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Baseline DDPM | 0.377 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Base | 0.377 | Not recorded | 6a3b64e7206542251d7c9a5e |

### MS-SSIM VAE

MS-SSIM: 0.587. Result ID: 6a3b9b95fbc373592c450c9e.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### VAE

MS-SSIM: 0.587. Result ID: 6a3b9b95fbc373592c450cc6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### MS-SSIM VAE

MS-SSIM: 0.579. Result ID: 6a3b9b95fbc373592c450c9d.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### VAE

MS-SSIM: 0.579. Result ID: 6a3b9b95fbc373592c450cc5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### DCGAN

MS-SSIM: 0.508. Result ID: 6a3b9b95fbc373592c450c9f.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### DCGAN

MS-SSIM: 0.508. Result ID: 6a3b9b95fbc373592c450cc8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### patch-based progressive training methodology for DDPMs

MS-SSIM: 0.481. Result ID: 6a3b9b95fbc373592c450c99.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Ours

MS-SSIM: 0.481. Result ID: 6a3b9b95fbc373592c450cbf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### DCGAN

MS-SSIM: 0.472. Result ID: 6a3b9b95fbc373592c450ca0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### DCGAN

MS-SSIM: 0.472. Result ID: 6a3b9b95fbc373592c450cc9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### patch-based progressive training methodology for DDPMs

MS-SSIM: 0.414. Result ID: 6a3b9b95fbc373592c450c9a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Ours

MS-SSIM: 0.414. Result ID: 6a3b9b95fbc373592c450cc0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Baseline DDPM

MS-SSIM: 0.412. Result ID: 6a3b9b95fbc373592c450c9b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69151e209131cea20194.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Base

MS-SSIM: 0.412. Result ID: 6a3b9b95fbc373592c450cc2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0d5.md>)

[Implementation](<https://github.com/hojonathanho/diffusion>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Baseline DDPM

MS-SSIM: 0.377. Result ID: 6a3b9b95fbc373592c450c9c.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69151e209131cea20194.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Base

MS-SSIM: 0.377. Result ID: 6a3b9b95fbc373592c450cc3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0d5.md>)

[Implementation](<https://github.com/hojonathanho/diffusion>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
